THE RIGHT PEOPLE: August 23

Launch HN: Depict.ai (YC S20) – Product recommendations for any e-commerce store Hey there! We are Oliver and Anton, and are founders at Depict.ai. We help online stores challenge Amazon by building recommender systems that don’t require any sales or behavioral data at all. Today, most recommender systems are based on a class of methods commonly called ‘collaborative filtering’ – which means that they generate recommendations based on a users’ past behavior. This method is successfully used by Amazon and Netflix (see the https://ift.tt/1O6ygl7 ). They are also very unsuccessfully used by smaller companies that lack the critical mass of historical behavioral data required to use those models effectively. This generally results in the cold start problem ( https://ift.tt/3l8qDS5… ) and a worse customer experience. We solve this by not focusing on understanding the customer but instead focus on understanding the product. The way we do this is with machine learning techniques that create vector representations of products based on the products’ images and descriptions, and recommend matching using these vector representations. More specifically, we have found a way to scrape the web and then train massive neural networks on e-commerce products. This makes it possible to leverage large amounts of product metadata to make truly impressive recommendations for any e-commerce store. One analogy we like is that just as almost no single company has enough sales or behavioral data to consistently predict, for instance, credit card frauds on their own, almost no e-commerce company has enough data to generate good recommendations based only on their own information. Stripe can make excellent fraud detection models by pooling transactions from many smaller companies, and we can do the same thing for personalizing e-commerce stores by pooling product metadata. Through A/B-tests we have proved that we can increase top-line revenue with 4-6% for almost any e-commerce store. To prove our value we offer the tests and setup 100% for free. We make money by taking a cut of the revenue uplift we generate in the A/B-tests. We have also found that the sales and decision cycle gets much shorter by being independent of customer’s user data. You can see us live at Staples Nordics and kitchentime.com, among others. Oliver and I have several years of experience applying recommender systems within e-commerce and education respectively and felt uneasy about a winner-takes-it-all development where the largest companies could use their data supremacy to out-personalize any smaller company. Our goal is to build a company that can offer the best personalization to any e-commerce store, not just the ones with enough data. Do you think our approach seems interesting, crazy, lazy or somewhere in the middle? We’d love any feedback – please feel free to shoot us comments below or DM, we’ll be here to answer your thoughts and gather feedback! /Depict.ai-team August 23, 2020 at 08:05AM

via Blogger https://ift.tt/2CXmbEI

(https://ift.tt/3gvnp7X

Show HN: An Android launcher based purely on touch gestures https://ift.tt/2QhLe8jTHE RIGHT PEOPLE https://ift.tt/3grVgydTHE RIGHT PEOPLE https://ift.tt/2Ey820Q https://ift.tt/2Ey820Q

Show HN: An Android launcher based purely on touch gestures https://ift.tt/31mxZd2 August 23, 2020 at 07:31AM

via Blogger https://ift.tt/34pukNt

(https://ift.tt/3j5AJS0

Show HN: Django REST Framework Boilerplate with JWT and Swagger https://ift.tt/2EqkVduTHE RIGHT PEOPLE https://ift.tt/2QkDBxUTHE RIGHT PEOPLE https://ift.tt/3goMrp9 https://ift.tt/3goMrp9

Show HN: Django REST Framework Boilerplate with JWT and Swagger https://ift.tt/34pr8kJ August 23, 2020 at 04:34AM

via Blogger https://ift.tt/2QlRBr6

(https://ift.tt/3lenXlQ

Show HN: Pingr – Uptime Monitoring https://ift.tt/3jb3Jb7THE RIGHT PEOPLE https://ift.tt/2EtrbBnTHE RIGHT PEOPLE https://ift.tt/32oK4xI https://ift.tt/32oK4xI

Show HN: Pingr – Uptime Monitoring https://pingr.io August 23, 2020 at 04:31AM

via Blogger https://ift.tt/2YrKvpP

(https://ift.tt/3gmOCcN

Show HN: Shieldon 2.0 Released Today https://ift.tt/32kkuJQTHE RIGHT PEOPLE https://ift.tt/32iAjRpTHE RIGHT PEOPLE https://ift.tt/3aRviTC https://ift.tt/3aRviTCTHE RIGHT PEOPLE https://ift.tt/3jclqalTHE RIGHT PEOPLE https://ift.tt/32gT5sy https://ift.tt/32gT5sy

Show HN: Shieldon 2.0 Released Today https://ift.tt/34owHQt August 22, 2020 at 11:23PM

via Blogger https://ift.tt/3j3rVfm

(https://ift.tt/31mbB3u

via Blogger https://ift.tt/3aPl4mN

(https://ift.tt/2CWR4sU

Show HN: Using rust to write shell-script like tasks https://ift.tt/34peS3RTHE RIGHT PEOPLE https://ift.tt/2Ei6c4GTHE RIGHT PEOPLE https://ift.tt/3aNmleh https://ift.tt/3aNmlehTHE RIGHT PEOPLE https://ift.tt/3l9hZD1THE RIGHT PEOPLE https://ift.tt/3j687YJ https://ift.tt/3j687YJ

Show HN: Using rust to write shell-script like tasks https://ift.tt/2V3sRpn August 22, 2020 at 10:04PM

via Blogger https://ift.tt/34qCTr6

(https://ift.tt/3hpdF01

via Blogger https://ift.tt/2YppmMK

(https://ift.tt/2EvT37D

Show HN: Shieldon 2.0 Released Today https://ift.tt/32kkuJQTHE RIGHT PEOPLE https://ift.tt/32iAjRpTHE RIGHT PEOPLE https://ift.tt/3aRviTC https://ift.tt/3aRviTC

Show HN: Shieldon 2.0 Released Today https://ift.tt/34owHQt August 22, 2020 at 11:23PM

via Blogger https://ift.tt/3j3rVfm

(https://ift.tt/31mbB3u

Show HN: Using rust to write shell-script like tasks https://ift.tt/34peS3RTHE RIGHT PEOPLE https://ift.tt/2Ei6c4GTHE RIGHT PEOPLE https://ift.tt/3aNmleh https://ift.tt/3aNmleh

Show HN: Using rust to write shell-script like tasks https://ift.tt/2V3sRpn August 22, 2020 at 10:04PM

via Blogger https://ift.tt/34qCTr6

(https://ift.tt/3hpdF01

THE RIGHT PEOPLE

Featured post

INTERVIEW WITH frankie(n)

Monday, August 24, 2020

Show HN: Creating a web app that looks like an old operational system https://ift.tt/32hf6HvTHE RIGHT PEOPLE https://ift.tt/31o7LHaTHE RIGHT PEOPLE https://ift.tt/3lfnuQr https://ift.tt/3lfnuQr

Show HN: Boethius, smart flashcards for the classical liberal arts https://ift.tt/31p9wUtTHE RIGHT PEOPLE https://ift.tt/2FKc9HSTHE RIGHT PEOPLE https://ift.tt/3gohiCb https://ift.tt/3gohiCb

Sunday, August 23, 2020

Show HN: Pingr – Uptime Monitoring https://ift.tt/3jb3Jb7THE RIGHT PEOPLE https://ift.tt/2EtrbBnTHE RIGHT PEOPLE https://ift.tt/32oK4xI https://ift.tt/32oK4xITHE RIGHT PEOPLE https://ift.tt/3laKVdQTHE RIGHT PEOPLE https://ift.tt/3gh9p1m https://ift.tt/3gh9p1m

Show HN: Boook.link – Share a book with links to all stores https://ift.tt/31jAcG3THE RIGHT PEOPLE https://ift.tt/2FTIjRzTHE RIGHT PEOPLE https://ift.tt/2Yt5Y1t https://ift.tt/2Yt5Y1t

Show HN: How we adapted our classrooms for videoconferencing https://ift.tt/3hnrKuNTHE RIGHT PEOPLE https://ift.tt/34okV8QTHE RIGHT PEOPLE https://ift.tt/34q3Uep https://ift.tt/34q3Uep

Launch HN: Depict.ai (YC S20) – Product recommendations for any e-commerce store https://ift.tt/31mdoFNTHE RIGHT PEOPLE https://ift.tt/2EsKN8ITHE RIGHT PEOPLE https://ift.tt/2CSnuER https://ift.tt/2CSnuER